摘要
现实生活中存在的网络大多是包含多种类型节点和边的异构网络,比同构网络融合了更多信息且包含更丰富的语义信息。异构网络表示学习拥有强大的建模能力,可以有效解决异构网络的异质性,并将异构网络中丰富的结构和语义信息嵌入到低维节点表示中,以便于下游任务应用。通过对当前国内外异构网络表示学习方法进行归纳分析,综述了异构网络表示学习方法的研究现状,对比了各类别模型之间的特点,介绍了异构网络表示学习的相关应用,并对异构网络表示学习方法的发展趋势进行了总结与展望,提出今后可在以下方面进行深入探讨:1)避免预先定义元路径,应充分释放模型的自动学习能力;2)设计适用于动态和大规模网络的异构网络表示学习方法。
Most of the real-life networks are heterogeneous networks that contain multiple types of nodes and edges,and heterogeneous networks integrate more information and contain richer semantic information than homogeneous networks.Heterogeneous network representation learning to have powerful modeling capabilities,enables to solve the heterogeneity of heterogeneous networks effectively,and to embed the rich structure information and semantic information of heterogeneous networks into low-dimensional node representations to facilitate downstream task applications.Through sorting out and classifying the current heterogeneous network representation learning methods at home and abroad,reviewed the current research status of heterogeneous network representation learning methods,compared the characteristics of each category model,introduced the related applications of heterogeneous network representation learning,and summarized and prospected the development trend of heterogeneous network representation learning methods.It is proposed that in-depth discussion can be carried out in the following aspects in future:First,avoid predefined meta-paths and fully release the automatic learning capabilities of the model;Second,design heterogeneous network representation learning method suitable for dynamic and large-scale networks.
作者
王建霞
刘梦琳
许云峰
张妍
WANG Jianxia;LIU Menglin;XU Yunfeng;ZHANG Yan(School of Information Science and Engineering,Hebei University of Science and Technology,Shijiazhuang,Hebei 050018,China)
出处
《河北科技大学学报》
CAS
北大核心
2021年第1期48-59,共12页
Journal of Hebei University of Science and Technology
基金
中国留学基金委地方合作项目(201808130283)
中国教育部人工智能协同育人项目(201801003011)
河北科技大学校立课题(82/1182108)。
关键词
计算机神经网络
异构网络
表示学习
图神经网络
建模能力
computer neural network
heterogeneous network
representation learning
graph neural network
modeling copabilities
